A Batch, Off-Policy, Actor-Critic Algorithm for Optimizing the Average Reward

Abstract

We develop an off-policy actor-critic algorithm for learning an optimal policy from a training set composed of data from multiple individuals. This algorithm is developed with a view towards its use in mobile health.

Cited by in corpus (8)

• Reinforcement Learning in Healthcare: A Survey
• Batch Policy Learning in Average Reward Markov Decision Processes
• Off-Policy Estimation of Long-Term Average Outcomes with Applications to Mobile Health
• Effective Warm Start for the Online Actor-Critic Reinforcement Learning based mHealth Intervention
• Latent-state models for precision medicine
• Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning
• Robust Actor-Critic Contextual Bandit for Mobile Health (mHealth) Interventions
• Sufficient Markov Decision Processes with Alternating Deep Neural Networks